黑龙江省农业机械化作业水平预测方法

黑龙江省农机化作业水平的预测是一个复杂的非线性系统，其发展变化具有增长性和波动性，对于拟合的方法要求较高。该文对黑龙江省农机化作业水平预测方法进行研究，在传统预测模型灰色GM(1，1)模型、平滑预测模型和回归预测模型的基础上建立了基础预测模型，并与BP神经网络模型组合，建立了灰色神经网络、平滑回归神经网络等组合预测模型，并预测了黑龙江省2008～2015年的农机化耕、种、收、植保、灌溉作业水平。结果表明，新的预测方法拟合精度高、有效、可行，为农机化作业水平的预测提供了一条新的途径；黑龙江省机耕、机播、植保作业水平很高，但是机收作业水平不高，机械化灌溉是主要的瓶颈，需要进一步发展。

Prediction method for the operation level of agricultural mechanization in Heilongjiang Province

The level of operation of agricultural mechanization is a complicated non-linear system, whose developmental changes have dual trends of increase and fluctuation in Heilongjiang Province, and has a high request to the fitting method. Through conducting the research on prediction method for operation level of agricultural mechanization, this study established basic prediction models based on tradition prediction models such as GM(1,1), smoothness and regression. The authors also combined the merits of tradition prediction models and BP neural network to establish comprehensive models, such as serial grey neural network, serial smoothness neural network, etc. The operation level of agricultural mechanization such as ploughing, sowing, harvesting, plant protection and irrigation in Heilongjiang Province from 2008 to 2015 were predicted. The results validate the effectiveness of the proposed models, and provide a new method for predicting the operation level of agricultural mechanization; mechanization level of ploughing, sowing, harvesting are higher than the other production links, irrigation is the main bottleneck, and needs to be further enhanced